We present SDialog, an MIT-licensed open-source Python toolkit that unifies dialog generation, evaluation and mechanistic interpretability into a single end-to-end framework for building and analyzing LLM-based conversational agents. Built around a standardized \texttt{Dialog} representation, SDialog provides: (1) persona-driven multi-agent simulation with composable orchestration for controlled, synthetic dialog generation, (2) comprehensive evaluation combining linguistic metrics, LLM-as-a-judge and functional correctness validators, (3) mechanistic interpretability tools for activation inspection and steering via feature ablation and induction, and (4) audio generation with full acoustic simulation including 3D room modeling and microphone effects. The toolkit integrates with all major LLM backends, enabling mixed-backend experiments under a unified API. By coupling generation, evaluation, and interpretability in a dialog-centric architecture, SDialog enables researchers to build, benchmark and understand conversational systems more systematically.
@article{arxiv.2512.09142,
title = {SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation},
author = {Sergio Burdisso and Séverin Baroudi and Yanis Labrak and David Grunert and Pawel Cyrta and Yiyang Chen and Srikanth Madikeri and Esaú Villatoro-Tello and Thomas Schaaf and Ricard Marxer and Petr Motlicek},
journal= {arXiv preprint arXiv:2512.09142},
year = {2025}
}
Comments
We have an old version of the paper at arXiv:2506.10622, we will update this old version instead (even though the authors and the title have changed since this first old version)